Tutorial on ASR inference and alignment with CTC model

gaBERT – an Irish Language Model

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

facebookresearch/libri-light, blog

Libri-light Data Preparation and Download

fairseq/examples/textless_nlp/gslm/speech2unit/clustering

fairseq/cpc_feature_reader.py

fairseq/examples/textless_nlp/gslm

fairseq/resynthesize_speech.py

flashlight/InferenceAndAlignmentCTC.ipynb

libri-light/make_vad_inputs.py

libri-light/data_preparation

Data Preparation · flashlight/wav2letter Wiki

libri-light/wl_decoder.py

format-corpus/pdfCabinetOfHorrors

[Text and tables Extraction from docx in Python by Mukesh Kumar Medium](https://medium.com/@Mukesh_Kumar/text-extraction-from-docx-readable-pdf-and-scanned-pdf-formats-in-python-b6c5712271ee)

language-resources/make-alignable-symbols.cc